Claude Sonnet 5.5 Crash GPT-6-Sol !!
I test Claude Sonnet 5.5 in a hard test that is recreating real life ship test in sea , seeing if it can do a good job But i was surprice that it make the result of GPT-6-Sol and DeepSeek v4.1 flash look like a toy compared to a Dragon
I ranked ChatGPT, Claude, Gemini, Grok and DeepSeek for AI trading, from S tier to F tier.
Which one did I get wrong? Tell me in the comments. Join the free 7-day AI trading challenge: financial advice. Backtests are not a promise of future results.
Who is missing from this song: Apple, Amazon, DeepSeek or someone else?
SuperLinear - Slopcore made with Deepseek v4.1 with Hermes and ComfyUI with MiniMax H3 and Qwen Image 2.1 running locally, it took over 12 hours.
You have reached the end of the archive
All of deepseek